Zhiqiang Qu

Zhiqiang Qu

Auto-generated profile, based on publicly available information

Zhiqiang Qu

Joint Laboratory of International Cooperation on Structural Mechanics of Composite Materials for Electronic Devices and the School of Mechano-Electronic Engineering, Xidian University, Xian, Shaanxi, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 September 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
YLYichen Liu
Yichen Liu
ZQZhiqiang Qu
Zhiqiang Qu
Guo ZhengGuo Zheng
Guo Zheng
YJYe Junjie
Ye Junjie
Accurate power line detection is critical for unmanned aerial vehicle (UAV)-based inspection systems. However, the detection accuracy is severely compromised by visually complex backgrounds characterized by similar textures and environmental interference, which often lead to substantial false-positives and false-negatives in detection results. To address these limitations, we propose a novel Uncertainty Region Modeling and Calibration Network (URMCNet), which incorporates an Uncertainty Region Modeling and Calibration Strategy that explicitly models and calibrates regions prone to false positives and false negatives, so as to enhance the accuracy of power line detection. The core component of URMCNet is the Primary Feature Calibration Mechanism, which incorporates the False-Positive Region Suppression Module and the False-Negative Region Compensation Module. These two modules adaptively calibrate uncertain regions, thereby making the feature representation more accurate and comprehensive. Furthermore, we introduce a High-Frequency Aware Fusion Decoder, which effectively restores the fine-grained details, thereby guaranteeing the continuity of the prediction results. The comprehensive experimental results demonstrate that URMCNet significantly outperforms state-of-the-art methods on several key performance metrics on the publicly available VITLD and TTPLA datasets.